New Research Shows Promise and Limitations of Physicians Working with GPT-4 for Decision Making

Published in JAMA Network Open, a collaborative team of researchers from the University of Minnesota Medical School, Stanford University, Beth Israel Deaconess Medical Center and the University of Virginia studied how well doctors used GPT-4 - an artificial intelligence (AI) large language model system - for diagnosing patients.

The study was conducted with 50 U.S.-licensed physicians in family medicine, internal medicine and emergency medicine. The research team found that the availability of GPT-4 to physicians as a diagnostic aid did not significantly improve clinical reasoning compared to conventional resources. Other key findings include:

  • GPT-4 alone demonstrated significantly better scores in diagnostic performance, surpassing the performance of clinicians using conventional diagnostic online resources and clinicians assisted by GPT-4.
  • There was no significant enhancement in diagnostic performance with the addition of GPT-4 when assessing clinicians using GPT-4 against clinicians using conventional diagnostic resources.

"The field of AI is expanding rapidly and impacting our lives inside and outside of medicine. It is important that we study these tools and understand how we best use them to improve the care we provide as well as the experience of providing it," said Andrew Olson, MD, a professor at the U of M Medical School and hospitalist with M Health Fairview. "This study suggests that there are opportunities for further improvement in physician-AI collaboration in clinical practice."

These results underline the complexity of integrating AI into clinical practice. While GPT-4 alone showed promising results, the integration of GPT-4 as a diagnostic aid alongside clinicians did not significantly outperform the use of conventional diagnostic resources. This suggests a nuanced potential for AI in healthcare, emphasizing the importance of further exploration into how AI can best support clinical practice. Further, more studies are needed to understand how clinicians should be trained to use these tools.

The four collaborating institutions have launched a bi-coastal AI evaluation network - known as ARiSE - to further evaluate GenAI outputs in healthcare.

Funding for this research was provided by the Gordon and Betty Moore Foundation.

Goh E, Gallo R, Hom J, Strong E, Weng Y, Kerman H, Cool JA, Kanjee Z, Parsons AS, Ahuja N, Horvitz E, Yang D, Milstein A, Olson APJ, Rodman A, Chen JH.
Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial.
JAMA Netw Open. 2024 Oct 1;7(10):e2440969. doi: 10.1001/jamanetworkopen.2024.40969

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

AI Spots Hidden Signs of Depression in S…

Depression is one of the most common mental health challenges, but its early signs are often overlooked. It is often linked to reduced facial expressivity. However, whether mild depression or...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...